Geometric ML | SmartUQ

Webinars

Machine Learning for Spatial and Temporal Response Prediction
This webinar introduces SmartUQ’s Spatial/Temporal Emulator and Varying Geometry Module.

Watch Here

Machine Learning for Narrowing the Simulation-Test Gap
This 60-minute Webinar will focus on statistical calibration, a machine learning process used to quantify uncertainties (both parameter and model form) in simulations as a means for narrowing the simulation-physical test gap.

Watch Here

White Papers

SmartUQ: Pushing the Boundaries of Engineering Analytics
As simulation, monitoring, and testing techniques become more sophisticated and produce increasing quantities of data, the need for a powerful engineering analytics tool to accurately and efficiently extract information and insights from the data has never been greater.
Introduction to SmartUQ Analytics and Digital Twins
This paper introduces SmartUQ’s predictive analytics capabilities and how analytics like Bayesian calibration can be applied to a digital twin.

Request Here

What is Physics AI?

Physics AI can be understood as a form of geometric machine learning, where the geometry itself encodes part of the underlying physical behavior of a system. In this framework, spatial structure, topology, and geometric variation are not just inputs but fundamental carriers of physical information.

SmartUQ's Varying Geometry Emulation: Advanced Geometric Machine Learning

SmartUQ’s varying geometry emulation directly supports building Physis AI models by enabling machine learning models—based on advanced Gaussian processes—to learn from and operate on complex, irregular, and changing geometries. By moving beyond traditional fixed-topology assumptions, SmartUQ provides a practical, data-efficient approach to Physics AI that captures both geometric and physical relationships with low computational cost.

Key Advantages and Capabilities

Handles Irregular, Non-Parametric, Variable Geometries:
- Unlike typical deep-learning frameworks that demand extensive preprocessing or fixed-topology meshes, SmartUQ's varying geometry emulation uses advanced kernel-based methods, specifically Gaussian processes.
- Directly builds surrogate models from irregular and variable datasets.
- Uniquely capable of managing significant variations in geometry, topology, or spatial coordinates between simulations or experimental runs.
Direct Modeling from Point Cloud Data:
- Employs fully nonparametric methods to construct predictive models directly from point cloud data.
- Highly relevant for unstructured datasets, such as those from Lidar scans, experimental measurement points, or adaptive mesh simulations.
- Reduces preprocessing effort, maintains original data integrity, and captures nuanced spatial relationships without the need for parameterized geometries or human feature identification .
Efficient Bayesian Optimization:
- Utilizes Gaussian process-based Bayesian optimization methodologies.
- Enables efficient navigation of complex design spaces, requiring fewer simulations or experimental runs compared to traditional neural networks and deep learning.
- Results in significant cost and time savings, especially beneficial in computationally intensive engineering applications.

A Robust Alternative to Neural Network based Geometric Deep Learning

SmartUQ’s varying geometry emulation technology offers a robust, adaptable, and computationally efficient alternative to conventional geometric deep learning. Its kernel-based Gaussian process approach easily handles changing geometries and irregular datasets with fewer data points and normal workstations, making it ideal for challenging engineering tasks that demand precise modeling from diverse and dynamic geometric data sources. This is particularly important for Physics AI, where the geometry itself encodes the underlying physics—enabling models to more accurately capture real-world behavior, generalize across design variations, and maintain fidelity to physical relationships without requiring massive datasets or computational resources.